Single-image Deraining And Hispathological Image Classification Based On Incoherent Dictionary Learning

Sparse representation is a signal transformation method that decomposes a signal into a linear combination of atoms in an overcomplete dictionary.The most of elements in a linearly combined coefficient is close to zero.Because the sparse representation can automatically extract the hidden feature information of various types of pictures,so it provides a new idea for image restoration and recognition.In the sparse representation theory,the design of the dictionary is a key issue.In view of the existing problems in the existing dictionary learning algorithms in specific application areas,the following work has been done in this paper:(1)The incoherent dictionary learning and sparse representation algorithm was present and it was applied to single-image rain removal.The incoherence of the dictionary was introduced to design a new objective function in the dictionary learning,which addressed the problem of reducing the similarity between rain atoms and non-rain atoms.The divisibility of rain dictionary and non-rain dictionary could be ensured.The high frequency in the rain image could be decomposed into a rain component and a non-rain component by performing sparse coding based learned incoherent dictionary,then the non-rain component in the high frequency and the low frequency were fused to remove rain.Experimental results demonstrate that the learned incoherent dictionary has better performance of sparse representation.The recovered rain-free image has less residual rain,and preserves effectively the edges and details.So the visual effect of recovered image is more sharpness and natural.(2)This paper presents a hispathological image classification algorithm which is based on incoherent dictionary learning and sparse representation.a more discriminative incoherent dictionary is obtained by introducing the coherence of the dictionary,and the iterative alternating projection method is used to reduce the degree of similarity between atoms,and the subspace rotation optimization method is used to optimize the sparse representation performance of incoherent dictionary,Experimental results show that the learning dictionary of this paper is more discriminative and obtains better classification performance.